© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2173
    Prev
    Next
    INDEX
    Explanations

    Spatial Query and Deep Thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     increased
    -1.09
    People
    -1.00
    Only
    -0.99
     improved
    -0.96
     perla
    -0.94
     increase
    -0.94
     actually
    -0.94
     decrease
    -0.92
     people
    -0.91
    When
    -0.90
    POSITIVE LOGITS
     area
    1.12
     level
    1.01
     tenisky
    1.00
    sbereich
    0.98
    bereich
    0.96
    Psycho
    0.95
     zone
    0.95
     vicinity
    0.94
     psychological
    0.93
     nivå
    0.91
    Activations Density 0.007%

    No Known Activations